Add prompt injection and guardrails security guide#1113
Conversation
404a00e to
42e3327
Compare
|
🌿 Preview your docs: https://vapi-preview-019f86ff-08d5-757a-bc1c-edb73b9b00f6.docs.buildwithfern.com |
42e3327 to
9efd059
Compare
|
🌿 Preview your docs: https://vapi-preview-019f8712-e5ad-707d-8ae5-8fb12ea6c057.docs.buildwithfern.com |
9efd059 to
db030ff
Compare
|
🌿 Preview your docs: https://vapi-preview-019f8725-83ae-743a-886e-51496c0cc1b0.docs.buildwithfern.com |
|
🌿 Preview your docs: https://vapi-preview-019f8731-e3c5-72ab-8980-2039a4c86a15.docs.buildwithfern.com |
0ac10c2 to
db70d58
Compare
|
🌿 Preview your docs: https://vapi-preview-019f8ad1-de79-70f8-a062-5b380e8fa217.docs.buildwithfern.com |
|
🌿 Preview your docs: https://vapi-preview-019f8ada-060c-759a-a8ac-02b34579bf61.docs.buildwithfern.com |
|
🌿 Preview your docs: https://vapi-preview-019f8add-66c5-74ad-83a1-6214047a7509.docs.buildwithfern.com |
e07d78b to
2223e23
Compare
|
🌿 Preview your docs: https://vapi-preview-019f8b35-2dd1-7419-a463-c54eaed84110.docs.buildwithfern.com |
|
🌿 Preview your docs: https://vapi-preview-019f8b39-47e9-778b-b99d-f30652367575.docs.buildwithfern.com |
ae77c4f to
f309370
Compare
|
🌿 Preview your docs: https://vapi-preview-019f8b3d-373a-7013-bec7-a03c6c59be4d.docs.buildwithfern.com |
|
🌿 Preview your docs: https://vapi-preview-019f8b41-c14c-7725-a7fb-5d174d43d852.docs.buildwithfern.com |
f309370 to
14b4296
Compare
|
🌿 Preview your docs: https://vapi-preview-019f8b46-ded4-733b-99c8-605e77a44baa.docs.buildwithfern.com |
14b4296 to
ae4c39a
Compare
|
🌿 Preview your docs: https://vapi-preview-019f8b58-6aa7-77d1-9115-56062c8c8157.docs.buildwithfern.com |
|
🌿 Preview your docs: https://vapi-preview-019f8b5c-5339-74ce-b5c1-f12c170b35bc.docs.buildwithfern.com |
|
🌿 Preview your docs: https://vapi-preview-019f8b63-512a-725f-8827-5d65baa9340d.docs.buildwithfern.com |
|
🌿 Preview your docs: https://vapi-preview-019f8b6b-360f-7274-be1c-0d64af5900c8.docs.buildwithfern.com |
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
ae4c39a to
2a072b6
Compare
|
🌿 Preview your docs: https://vapi-preview-019f8b9a-ad25-717f-827d-8c5b08b9138c.docs.buildwithfern.com |
Description
Adds a new Prompt injection and guardrails guide under Security and privacy. It covers the layers available to protect an assistant against prompt injection and data exposure.
fern/security-and-privacy/prompt-injection-and-guardrails.mdxfern/docs.ymlcompliancePlan.securityFilterPlan), then keeping sensitive data out of context (the return-a-status pattern, stored credentials, and tool argument encryption)securityFilterUtil.ts,security.types.ts) and the existing tool-argument-encryption guideOpen questions for review
sanitizevsreplacefilter modes. InsecurityFilterUtil.tsthese run identical code (both substitute the matched phrase withreplacementText). The doc currently documentssanitizeand notes thatreplacebehaves identically. Is that the intended behavior, or shouldsanitizestrip to empty whilereplacesubstitutes? The original author (Adi) has left, so this needs a second opinion before we commit to the wording.prompt-injectionregexes. That is useful for honest users, but it also tells an attacker exactly how to word around the filter. Keep them, or describe the categories and link the API reference instead?Testing Steps
fern docs devor navigate to preview deployment